© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14501
    Prev
    Next
    INDEX
    Explanations

    issue inode number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.13
    ä¸Ģ个个
    -0.12
    çļĦä¸Ģç§į
    -0.12
     ones
    -0.12
    çļĦä¸Ģ種
    -0.11
    çļĦä¸ĢäºĽ
    -0.11
    è¿Ļä¸Ģ
    -0.10
    æĹłä¸Ģ
    -0.10
    ä¸Ģå¾ĭ
    -0.10
    ä¸Ģè¯į
    -0.10
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.18
    åĴĮä¸Ģ个
    0.15
    åı«åģļ
    0.09
    åIJįåı«
    0.09
     namens
    0.08
    åIJį为
    0.07
    åĬ²åĦ¿
    0.07
    缩影
    0.07
    /
    0.07
    åIJįåŃĹåı«
    0.06
    Activations Density 0.012%

    No Known Activations